Index index by Group index by Distribution index by Vendor index by creation date index by Name Mirrors Help Search

python313-comfy-aimdo-0.4.15-1.1 RPM for noarch

From OpenSuSE Ports Tumbleweed for noarch

Name: python313-comfy-aimdo Distribution: openSUSE Tumbleweed
Version: 0.4.15 Vendor: openSUSE
Release: 1.1 Build date: Tue Aug 25 18:59:43 2026
Group: Unspecified Build host: reproducible
Size: 145579 Source RPM: python-comfy-aimdo-0.4.15-1.1.src.rpm
Packager: http://bugs.opensuse.org
Url: https://github.com/Comfy-Org/comfy-aimdo
Summary: AI Model Dynamic Offloader for ComfyUI (pure-Python fallback)
 
AIMDO (AI Model Dynamic Offloader) is a PyTorch VRAM allocator used by
ComfyUI to offload model weights under memory pressure. This build ships
the pure-Python fallback. The native CUDA/HIP allocator is not compiled:
it requires CUDA 12.8+ and a CUDA-enabled PyTorch, which Factory does
not provide. Without the native module, init() returns False and ComfyUI
continues without AIMDO.

Provides

Requires

License

GPL-3.0-only

Changelog

* Tue Aug 25 2026 Martin Pluskal <mpluskal@suse.com>
  - Update to 0.4.15:
    * Windows shared-memory detection now keeps 512 MB of VRAM headroom
      instead of the 768 MB introduced in 0.4.14 when the free-memory
      figure is read from NVML rather than from cuMemGetInfo()
    * That Windows-only constant is the entire release; the Python code
      shipped by this package is unchanged from 0.4.14
* Sun Aug 23 2026 Martin Pluskal <mpluskal@suse.com>
  - Stop warning "Could not autodetect AIMDO implementation, assuming
    Nvidia" on every start: add
    comfy-aimdo-detect-vendor-without-local-version.patch
    * the vendor check looked for "+cu" or "+rocm" in the PyTorch
      version string, which only upstream's own wheels carry, so a
      distribution PyTorch never matched and the code then guessed
      Nvidia; it now reads the cuda and hip attributes that the same
      version module already defines
    * when PyTorch has neither, there is no allocator to load, so
      init() reports failure with an informational message instead of
      warning about a vendor it never really selected
    * %check now exercises that path
* Sun Aug 23 2026 Martin Pluskal <mpluskal@suse.com>
  - Update to 0.4.14:
    * README now documents AMD GPU (ROCm 7+) support alongside Nvidia
      (CUDA 12.8+); the HIP backend itself already shipped in 0.4.13
      and is unchanged in this release
    * Windows shared-memory detection reserves a larger VRAM headroom
      (768 MB) when the free-memory figure comes from NVML rather than
      from cuMemGetInfo()
    * No changes to the pure-Python fallback shipped by this package
* Fri Aug 21 2026 Martin Pluskal <mpluskal@suse.com>
  - Initial package of python-comfy-aimdo 0.4.13:
    * Pure-Python fallback; native CUDA/HIP allocator is not built
      (needs CUDA 12.8+ and a CUDA-enabled PyTorch)
    * Require python-torch >= 2.8.0

Files

/usr/lib/python3.13/site-packages/comfy_aimdo
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/INSTALLER
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/METADATA
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/RECORD
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/REQUESTED
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/WHEEL
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/licenses
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/licenses/LICENSE
/usr/lib/python3.13/site-packages/comfy_aimdo-0.4.15.dist-info/top_level.txt
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/_version.cpython-313.opt-1.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/_version.cpython-313.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/control.cpython-313.opt-1.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/control.cpython-313.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/host_buffer.cpython-313.opt-1.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/host_buffer.cpython-313.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/model_mmap.cpython-313.opt-1.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/model_mmap.cpython-313.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/model_vbar.cpython-313.opt-1.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/model_vbar.cpython-313.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/torch.cpython-313.opt-1.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/torch.cpython-313.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/vram_buffer.cpython-313.opt-1.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/__pycache__/vram_buffer.cpython-313.pyc
/usr/lib/python3.13/site-packages/comfy_aimdo/_version.py
/usr/lib/python3.13/site-packages/comfy_aimdo/control.py
/usr/lib/python3.13/site-packages/comfy_aimdo/host_buffer.py
/usr/lib/python3.13/site-packages/comfy_aimdo/model_mmap.py
/usr/lib/python3.13/site-packages/comfy_aimdo/model_vbar.py
/usr/lib/python3.13/site-packages/comfy_aimdo/torch.py
/usr/lib/python3.13/site-packages/comfy_aimdo/vram_buffer.py
/usr/share/doc/packages/python313-comfy-aimdo
/usr/share/doc/packages/python313-comfy-aimdo/README.md
/usr/share/licenses/python313-comfy-aimdo
/usr/share/licenses/python313-comfy-aimdo/LICENSE

Generated by rpm2html 1.8.1

Fabrice Bellet, Sun Aug 30 00:27:02 2026